Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-5.4 nano
58
0/8 categoriesQwen3.5-122B-A10B
71
Winner · 5/8 categoriesGPT-5.4 nano· Qwen3.5-122B-A10B
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. GPT-5.4 nano only becomes the better choice if you need the larger 400K context window.
Qwen3.5-122B-A10B is clearly ahead on the aggregate, 71 to 58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5-122B-A10B's sharpest advantage is in knowledge, where it averages 81.6 against 53.2. The single biggest benchmark swing on the page is OSWorld-Verified, 39% to 58%.
GPT-5.4 nano is also the more expensive model on tokens at $0.20 input / $1.25 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. GPT-5.4 nano gives you the larger context window at 400K, compared with 262K for Qwen3.5-122B-A10B.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | GPT-5.4 nano | Qwen3.5-122B-A10B |
|---|---|---|
| AgenticQwen3.5-122B-A10B wins | ||
| Terminal-Bench 2.0 | 46.3% | 49.4% |
| OSWorld-Verified | 39% | 58% |
| MCP Atlas | 56.1% | — |
| Toolathlon | 35.5% | — |
| tau2-bench | 92.5% | 79.5% |
| BrowseComp | — | 63.8% |
| CodingQwen3.5-122B-A10B wins | ||
| SWE-bench Pro | 52.4% | — |
| SWE-bench Verified | — | 72% |
| LiveCodeBench | — | 78.9% |
| Multimodal & GroundedQwen3.5-122B-A10B wins | ||
| MMMU-Pro | 66.1% | 76.9% |
| MMMU-Pro w/ Python | 69.5% | — |
| OmniDocBench 1.5 | 0.2419 | — |
| ReasoningQwen3.5-122B-A10B wins | ||
| MRCRv2 | 38.7% | — |
| MRCR v2 64K-128K | 44.2% | — |
| MRCR v2 128K-256K | 33.1% | — |
| Graphwalks BFS 128K | 73.4% | — |
| Graphwalks Parents 128K | 50.8% | — |
| LongBench v2 | — | 60.2% |
| KnowledgeQwen3.5-122B-A10B wins | ||
| GPQA | 82.8% | 86.6% |
| HLE | 37.7% | — |
| HLE w/o tools | 24.3% | — |
| MMLU-Pro | — | 86.7% |
| SuperGPQA | — | 67.1% |
| Instruction Following | ||
| IFEval | — | 93.4% |
| Multilingual | ||
| MMLU-ProX | — | 82.2% |
| Mathematics | ||
| Coming soon | ||
Qwen3.5-122B-A10B is ahead overall, 71 to 58. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 39% and 58%.
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 81.6 versus 53.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 76.3 versus 52.4. GPT-5.4 nano stays close enough that the answer can still flip depending on your workload.
Qwen3.5-122B-A10B has the edge for reasoning in this comparison, averaging 60.2 versus 38.7. GPT-5.4 nano stays close enough that the answer can still flip depending on your workload.
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56 versus 42.9. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 66.1. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.